AUTHOR=Sabeghi Paniz , Kinkar Ketki K. , Castaneda Gloria del Rosario , Eibschutz Liesl S. , Fields Brandon K. K. , Varghese Bino A. , Patel Dakshesh B. , Gholamrezanezhad Ali 

TITLE=Artificial intelligence and machine learning applications for the imaging of bone and soft tissue tumors

JOURNAL=Frontiers in Radiology

VOLUME=Volume 4 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/radiology/articles/10.3389/fradi.2024.1332535

DOI=10.3389/fradi.2024.1332535

ISSN=2673-8740

ABSTRACT=Recent advancements in artificial intelligence (AI) and machine learning (ML) offer numerous opportunities in musculoskeletal (MSK) radiology to potentially bolster diagnostic accuracy, workflow efficiency, and predictive modeling. AI tools have the capability to assist radiologists in many tasks ranging from image segmentation, anomaly detection, and more.In bone and soft tissue tumor imaging, radiomics and deep learning show promise for malignancy stratification, grading, prognostication, and treatment planning. However, challenges like standardization, data integration, and ethical concerns regarding patient data need to be addressed before clinical translation. AI also faces obstacles in robust algorithm development due to limited disease incidence. While global initiatives aim to develop multitasking AI systems, multidisciplinary collaboration is crucial for successful AI integration into clinical practice.Robust approaches addressing challenges and embodying ethical practices are warranted to fully realize AI's potential for enhancing diagnostic accuracy and advancing patient care.• Deep learning models have been developed for diagnosing MSK tumors and show potential to achieve diagnostic efficacy comparable to radiologists in limited classification tasks. • AI algorithms can address issues related to variance in acquisition parameters and noise between MR scans using techniques like edge-preserving denoising and intensity standardization. • Multitasking AI systems that can efficiently perform multiple segmentation and analytical tasks at once hold promise for potentially useful prospective implementations in clinical practice.